Agents

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents

Single source1 source9 Oct 2026

arXiv:2510.10931v3 Announce Type: replace Abstract: While reinforcement learning (RL) enhances their ability to plan and reason across retrieval steps, we identify a critical failure mode in this setting: Tool-Call Hacking.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2510.10931

← Back to all developments · Signals are a development reported by more than one source. See the methodology.